## Die Suche ergab 80 Treffer

14. Feb 2009 12:45
Forum: Digitale Spiele / Digital Games
Thema: Noten?
Antworten: 7
Zugriffe: 4122

### Re: Noten?

Die Noten sind endlich da.
13. Dez 2008 17:35
Forum: Computer Vision 2
Thema: A3 P1
Antworten: 2
Zugriffe: 637

### Re: A3 P1

thank you for your help. Know I think it works finde
13. Dez 2008 17:35
Forum: Computer Vision 2
Thema: A3 P2
Antworten: 3
Zugriffe: 1146

### A3 P2

I don't manage to calculate the mrf_grad_log_prior correctly. I tried to compute the derivative analytically (computing the derivative of the students t distribution and divide it by the students t diestribution) and then do this for all four neighbors of a pixel. My idea was to construct a Matrix f...
13. Dez 2008 15:06
Forum: Computer Vision 2
Thema: A3 P1
Antworten: 2
Zugriffe: 637

### A3 P1

I have implemented the mrf log prior with Matrix operations and I get as result for big images always result -inf because so many multiplications of small values are round to 0.0000 in MATLAB.
How can I avoid this?
19. Nov 2008 16:09
Forum: Archiv
Thema: Testoptions
Antworten: 0
Zugriffe: 148

### Testoptions

Welche Testoption sollen wir für das erste Projekt verwenden?
19. Nov 2008 16:03
Forum: Archiv
Thema: 1. Projektaufgabe: zoo.arff
Antworten: 1
Zugriffe: 185

### Re: 1. Projektaufgabe: zoo.arff

Unter dem Link gibt es ein Jar datasets_UCI.jar
Das kann man runterladen und entpacken und darin ist ein ordner indem
auch das zoo.arff ist.
16. Nov 2008 18:48
Forum: Computer Vision 2
Thema: Assignment 2 Problem 3
Antworten: 4
Zugriffe: 897

### Re: Assignment 2 Problem 3

Essentially you are doing the same as in the reconstruction of the images. There you took the projections of the images and you projected them back from the subspace into the "full" space. Now you use random factors instead of the projected images. Compare for the Matlab manual of the function rand...
16. Nov 2008 15:36
Forum: Computer Vision 2
Thema: Assignment 2 Problem 3
Antworten: 4
Zugriffe: 897

### Re: Assignment 2 Problem 3

I have substracted the mean when doing the PCA. Thats clear to me. But if I choose a mouth m and want to project it in the eigenmouthspace, have I then to substract the mean from m before doing the projection? If looked to the slides 69 and 70 before and I thought they told me to do it this way. Las...
15. Nov 2008 18:41
Forum: Computer Vision 2
Thema: Assignment 2 Problem 3
Antworten: 4
Zugriffe: 897

### Assignment 2 Problem 3

I try to project a mouth image in the subspace of eigen-mouths. If I substract the mean mouth and then project the images of the reconstructed images get black. If I don't do this I get an reasonable result. Image below. Or is it wrong? Have I to substract the mean befor the projection? Or where is ...
6. Nov 2008 12:03
Forum: Computer Vision 2
Thema: Office hours
Antworten: 3
Zugriffe: 771

### Re: Office hours

And where will the office hour be?
5. Nov 2008 11:54
Forum: Computer Vision 2
Thema: Ex 1 P3
Antworten: 1
Zugriffe: 624

### Ex 1 P3

I don't clearly understand the last task on the exercise sheet (image sharpening). What are the two finest levels of the laplacian pyramid? Are these the images with the highest resolution? :?: Is it right only to multiply the finest to level matrices by a scalar to amplifie them? The image my perha...
2. Nov 2008 11:38
Forum: Computer Vision 2
Thema: ex 1 p3
Antworten: 4
Zugriffe: 916

### Re: ex 1 p3

Thank you very much !!
Now I got the right idea.
I was to concentrated on extracting the 2x2 blocks (of course) I think.
1. Nov 2008 16:45
Forum: Computer Vision 2
Thema: ex 1 p3
Antworten: 4
Zugriffe: 916

### Re: ex 1 p3

thank you for your help. I've read the whole guide. But there is no special idea I get from it how I can do this. :( Like I've written before I know how to extract the blocks but there is still no idea how to iterate over them without any loop. Or are there some special commands to use instead of pu...
31. Okt 2008 22:02
Forum: Computer Vision 2
Thema: ex 1 p3
Antworten: 4
Zugriffe: 916

### ex 1 p3

Has anybody an idea how to do the downsample and upsample without loops ?
I would need one loop to iterate over the 4x4 matrix blocks.
Is there some command for handling the matrix as block matrizes?